The thermal imaging pedestrian segmentation system has excellent performance in different illumination conditions, but it has some drawbacks(e.g., weak pedestrian texture information, blurred object boundaries). Meanwhile, high-performance large models have higher latency on edge devices with limited computing performance. To solve the above problems, in this paper, we propose a real-time thermal infrared pedestrian segmentation method. The feature extraction layers of our method consist of two paths. Firstly, we utilize the lossless spatial downsampling to obtain boundary texture details on the spatial path. On the context path, we use atrous convolutions to improve the receptive field and obtain more contextual semantic information. Then, the parameter-free attention mechanism is introduced at the end of the two paths for effective feature selection, respectively. The Feature Fusion Module (FFM) is added to fuse the semantic information of the two paths after selection. Finally, we accelerate method inference through multi-threading techniques on the edge computing device. Besides, we create a high-quality infrared pedestrian segmentation dataset to facilitate research. The comparative experiments on the self-built dataset and two public datasets with other methods show that our method also has certain effectiveness. Our code is available at https://github.com/mcjcs001/LEIPNet.

We present a reconfigurable deep learning pedestrian detection system for surveillance systems that detect people with shadows in different lighting and heavily occluded conditions. This work proposes a region-based CNN, combined with CMOS and thermal cameras to obtain human features even under poor lighting conditions. The main advantage of a reconfigurable system with respect to processor-based systems is its high performance and parallelism when processing large amount of data such as video frames. We discuss the details of hardware implementation in the proposed real-time pedestrian detection algorithm on a Zynq FPGA. Simulation results show that the proposed integrated approach of R-CNN architecture with cameras provides better performance in terms of accuracy, precision, and F1-score. The performance of Zynq FPGA was compared to other works, which showed that the proposed architecture is a good trade-off in terms of quality, accuracy, speed, and resource utilization.

Recently, many AI-aided layout design systems are developed to reduce tedious manual intervention based on deep learning. However, most methods focus on a specific generation task. This paper explores a challenging problem to obtain multiple layout design generation (LDG), which generates floor plan or urban plan from a boundary input under a unified framework. One of the main challenges of multiple LDG is to obtain reasonable topological structures of layout generation with irregular boundaries and layout elements for different types of design. This paper formulates the multiple LDG task as an image-to-image translation problem, and proposes a conditional generative adversarial network (GAN), called LDGAN, with adaptive modules. The framework of LDGAN is based on a generator-discriminator architecture, where the generator is integrated with conditional convolution constrained by the boundary input and the attention module with channel and spatial features. Qualitative and quantitative experiments were conducted on the SCUT-AutoALP and RPLAN datasets, and the comparison with the state-of-the-art methods illustrate the effectiveness and superiority of the proposed LDGAN.

GPUs have become the dominant computing units to meet the need of high performance in various computational fields. But the long operation latency causes the underutilization of on-chip computing resources, resulting in performance degradation when running parallel tasks on GPUs. A good warp scheduling strategy is an effective solution to hide latency and improve resource utilization. However, most current warp scheduling algorithms on GPUs ignore the ability of long operations to hide latency. In this paper, we propose a long-operation-first warp scheduling algorithm, LFWS, for GPU platforms. The LFWS filters warps in the ready state to a ready queue and updates the queue in time according to changes in the status of the warp. The LFWS divides the warps in the ready queue into long and short operation groups based on the type of operations in their instruction buffers, and it gives higher priority to the long-operating warp in the ready queue. This can effectively use the long operations to hide some of the latency from each other and enhance the system's ability to hide the latency. To verify the effectiveness of the LFWS, we implement the LFWS algorithm on a simulation platform GPGPU-Sim. Experiments are conducted over various CUDA applications to evaluate the performance of LFWS algorithm, compared with other five warp scheduling algorithms. The results show that the LFWS algorithm achieves an average performance improvement of 8.01% and 5.09%, respectively, over three traditional and two novel warp scheduling algorithms, effectively improving computational resource utilization on GPU.

Modern large scale distributed storage systems play a central role in data center and cloud storage, while node failure in data center is common. The lost data in failure node must be recovered efficiently. Locally repairable codes (LRCs) are designed to solve this problem. The locality of an LRC is the number of nodes that participate in recovering the lost data from node failure, which characterizes the repair efficiency. An LRC is called optimal if its minimum distance attains Singleton-type upper bound [1]. In this paper, using basic techniques of linear algebra over finite field, infinite optimal LRCs over extension fields are derived from a given optimal LRC over base field(or small field). Next, this paper investigates the relation between near-MDS codes with some constraints and LRCs, further, proposes an algorithm to determine locality of dual of a given linear code. Finally, based on near-MDS codes and the proposed algorithm, those obtained optimal LRCs are shown.

In human-computer interaction, acoustic scene classification (ASC) is one of the relevant research domains. In real life, the recorded audio may include a lot of noise and quiet clips, making it hard for earlier ASC-based research to isolate the crucial scene information in sound. Furthermore, scene information may be scattered across numerous audio frames; hence, selecting scene-related frames is crucial for ASC. In this context, an integrated convolutional neural network with a fusion attention mechanism (ICNN-FA) is proposed for ASC. Firstly, segmented mel-spectrograms as the input of ICNN can assist the model in learning the short-term time-frequency correlation information. Then, the designed ICNN model is employed to learn these segment-level features. In addition, the proposed global attention layer may gather global information by integrating these segment features. Finally, the developed fusion attention layer is utilized to fuse all segment-level features while the classifier classifies various situations. Experimental findings using ASC datasets from DCASE 2018 and 2019 indicate the efficacy of the suggested method.

In frequency hopping communication, time delay and Doppler shift incur interference. With the escalating upgrading of complicated interference, in this paper, the time-frequency two-dimensional (TFTD) partial Hamming correlation (PHC) properties of wide-gap frequency-hopping sequences (WGFHSs) with frequency shift are discussed. A bound on the maximum TFTD partial Hamming auto-correlation (PHAC) and two bounds on the maximum TFTD PHC of WGFHSs are got. Li-Fan-Yang bounds are the particular cases of new bounds for frequency shift is zero.

The orthogonal time frequency space (OTFS) technique proposed in recent years has excellent anti-Doppler frequency shift and time delay performance, enabling its application in high speed communication scenarios. In this article, a particle swarm optimization (PSO) signal detection algorithm for OTFS system is proposed, an adaptive mechanism for the individual learning factor and global learning factor in the speed formula of the algorithm is designed, and the position update method of the particles is improved, so as to increase the convergence accuracy and avoid the particles to fall into local optimum. The simulation results show that the improved PSO algorithm has the advantages of low bit error rate (BER) and high convergence accuracy compared with the traditional PSO algorithm, and has similar performance to the ideal state maximum likelihood (ML) detection algorithm with lower complexity. In the case of high Doppler shift, OTFS technology has better performance than orthogonal frequency division multiplexing (OFDM) technology by using improved PSO algorithm.

Internet of Things (IoT) devices are widely used in various fields. However, their limited computing resources make them extremely vulnerable and difficult to be effectively protected. Traditional intrusion detection systems (IDS) focus on high accuracy and low false alarm rate (FAR), making them often have too high spatiotemporal complexity to be deployed in IoT devices. In response to the above problems, this paper proposes an intrusion detection model of IoT based on the light gradient boosting machine (LightGBM). Firstly, the one-dimensional convolutional neural network (CNN) is used to extract features from network traffic to reduce the feature dimensions. Then, the LightGBM is used for classification to detect the type of network traffic belongs. The LightGBM is more lightweight on the basis of inheriting the advantages of the gradient boosting tree. The LightGBM has a faster decision tree construction process. Experiments on the TON-IoT and BoT-IoT datasets show that the proposed model has stronger performance and more lightweight than the comparison models. The proposed model can shorten the prediction time by 90.66% and is better than the comparison models in accuracy and other performance metrics. The proposed model has strong detection capability for denial of service (DoS) and distributed denial of service (DDoS) attacks. Experimental results on the testbed built with IoT devices such as Raspberry Pi show that the proposed model can perform effective and real-time intrusion detection on IoT devices.

Event detection and recognition are important for environmental monitoring in the Internet of things and cyber-physical systems. Low power wide area (LPWA) networks are one of the most powerful wireless sensor networks to support data gathering; however, they do not afford peak wireless access from sensors that detect significant changes in sensing data. Various data gathering schemes for event detection and recognition have been proposed. However, these do not satisfy the requirement for the three functions for the detection of the occurrence of an event, the recognition of the position of an event, and the recognition of spillover of impact from an event. This study proposes a three-stage data gathering scheme for LPWA. In the first stage, the access limitation based on the comparison between the detected sensing data and the high-level threshold is effective in reducing the simultaneous accessing sensors; thus, high-speed recognition of the starting event is achieved. In the second stage, the data centre station designates the sensor to inform the sensing data to achieve high accuracy of the position estimation of the event. In the third stage, all the sensors, except for the accessing sensors in the early stage, access the data centre. Owing to the exhaustive gathering of sensing data, the spillover of impact from the event can be recognised with high accuracy. We implement the proposed data gathering scheme for the actual wireless sensor system of the LPWA. From the computer simulation and experimental evaluation, we show the advantage of the proposed scheme compared to the conventional scheme.

With the recent commercialization of fifth-generation mobile communication systems (5G), wireless communications are being used in various fields. Accordingly, the number of situations in which sensitive information, such as personal data is handled in wireless communications is increasing, and so is the demand for confidentiality. To meet this demand, we proposed a chaos-based radio-encryption modulation that combines physical layer confidentiality and channel coding effects, and we have demonstrated its effectiveness through computer simulations. However, there are no demonstrations of performances using real signals. In this study, we constructed a transmission system using Universal Software Radio Peripheral, a type of software-defined radio, and its control software LabVIEW. We conducted wired transmission experiments for the practical use of radio-frequency encrypted modulation. The results showed that a gain of 0.45dB at a bit error rate of 10-3 was obtained for binary phase-shift keying, which has the same transmission efficiency as the proposed method under an additive white Gaussian noise channel. Similarly, a gain of 10dB was obtained under fading conditions. We also evaluated the security ability and demonstrated that chaos modulation has both information-theoretic security and computational security.

Intelligent traffic monitoring provides information support for autonomous driving, which is widely used in intelligent transportation systems (ITSs). A method for estimating vehicle moving target parameters based on millimeter-wave radars is proposed to solve the problem of low detection accuracy due to velocity ambiguity and Doppler-angle coupling in the process of traffic monitoring. First of all, a MIMO antenna array with overlapping elements is constructed by introducing them into the typical design of MIMO radar array antennas. The motion-induced phase errors are eliminated by the phase difference among the overlapping elements. Then, the position errors among them are corrected through an iterative method, and the angle of multiple targets is estimated. Finally, velocity disambiguation is performed by adopting the error-corrected phase difference among the overlapping elements. An accurate estimation of vehicle moving target angle and velocity is achieved. Through Monte Carlo simulation experiments, the angle error is 0.1° and the velocity error is 0.1m/s. The simulation results show that the method can be used to effectively solve the problems related to velocity ambiguity and Doppler-angle coupling, meanwhile the accuracy of velocity and angle estimation can be improved. An improved algorithm is tested on the vehicle datasets that are gathered in the forward direction of ordinary public scenes of a city. The experimental results further verify the feasibility of the method, which meets the real-time and accuracy requirements of ITSs on vehicle information monitoring.

The degree of reception of BS signals is affected by various factors. After routinely recording it at two observation points at two locations, we found that momentary upward and downward level shifts occurred multiple times, mainly during daytime. These level shifts were observed at one location. No such signal was sensed at the other location. After producing an algorithm to extract such momemtary level shifts, their statistical properties were investigated. Careful analyses, including assessment of the signal polarity, amplitude, duration, hours, and comparison with actual flight schedules and route information implied that these level shifts are attributable to the interference of direct and reflected waves from aircraft flying at approximately tropopause altitude. This assumption is further validated through computer simulations of BS signal interference.

Physical Unclonable Function (PUF) is a promising lightweight hardware security primitive that can extract device fingerprints for encryption or authentication. However, extracting fingerprints from either the chip or the board individually has security flaws and cannot provide hardware system-level security. This paper proposes a new Chip-PCB hybrid PUF(CPR PUF) in which Weak PUF on PCB is combined with Strong PUF inside the chip to generate massive responses under the control of challenges of on-chip Strong PUF. This structure tightly couples the chip and PCB into an inseparable and unclonable unit thus can verify the authenticity of chip as well as the board. To improve the uniformity and reliability of Chip-PCB hybrid PUF, we propose a lightweight key generator based on a reliability self-test and debiasing algorithm to extract massive stable and secure keys from unreliable and biased PUF responses, which eliminates expensive error correction processes. The FPGA-based test results show that the PUF responses after robust extraction and debiasing achieve high uniqueness, reliability, uniformity and anti-counterfeiting features. Moreover, the key generator greatly reduces the execution cost and the bit error rate of the keys is less than 10-9, the overall security of the key is also improved by eliminating the entropy leakage of helper data.

This paper proposes the new series highly integrated intelligent power module (IPM), which is developed to provide a ultra-compact, high performance and reliable motor drive system. Details of the key design technologies of the IPM is given and practical application issues such as electrical characteristics, system operation performance and power dissipation are discussed. Layout placement and routing have been optimized in order to reduce and balance the parasitic impedances. By implementing an innovative direct bonding copper (DBC) ceramic substrate, which can effectively dissipate heat, the IPM delivers a fully integrated power stages including two three-phase inverters, power factor correction (PFC) and rectifier in an ultra-compact 75.5mm × 30mm package, offering up to a 17.3 percent smaller space than traditional motor drive scheme.

Automatic modulation recognition(AMR) of radar signals is a currently active area, especially in electronic reconnaissance, where systems need to quickly identify the intercepted signal and formulate corresponding interference measures on computationally limited platforms. However, previous methods generally have high computational complexity and considerable network parameters, making the system unable to detect the signal timely in resource-constrained environments. This letter firstly proposes an efficient modulation recognition network(EMRNet) with tiny and low latency models to match the requirements for mobile reconnaissance equipments. One-dimensional residual depthwise separable convolutions block(1D-RDSB) with an adaptive size of receptive fields is developed in EMRNet to replace the traditional convolution block. With 1D-RDSB, EMRNet achieves a high classification accuracy and dramatically reduces computation cost and network paraments. The experiment results show that EMRNet can achieve higher precision than existing 2D-CNN methods, while the computational cost and parament amount of EMRNet are reduced by about 13.93× and 80.88×, respectively.

Previously, convolutional neural networks have made tremendous progress in target recognition based on micro-Doppler radar. However, these studies only considered the presence of one target at a time in the surveillance area. Simultaneous multi-targets recognition for surveillance radar remains a pretty challenging issue. To alleviate this issue, this letter develops a multi-instance multi-label (MIML) learning strategy, which can automatically locate the crucial input patterns that trigger the labels. Benefitting from its powerful target-label relation discovery ability, the proposed framework can be trained with limited supervision. We emphasize that only echoes from single targets are involved in training data, avoiding the preparation and annotation of multi-targets echo in the training stage. To verify the validity of the proposed method, we model two representative ground moving targets, i.e., person and wheeled vehicles, and carry out numerous comparative experiments. The result demonstrates that the developed framework can simultaneously recognize multiple targets and is also robust to variation of the signal-to-noise ratio (SNR), the initial position of targets, and the difference in scattering coefficient.

As ransomware inevitably overwrites existing data, SSDs can detect ransomware attacks by monitoring overwrites. The state-of-the-art technology uses a hash to monitor overwrites, which consumes tens of bytes of memory per I/O. To improve memory efficiency, we propose a bitmap-based overwrite detection method that uses only one bit per I/O.

In this letter, we propose a feature-based knowledge distillation scheme which transfers knowledge between intermediate blocks of teacher and student with flow-based architecture, specifically Normalizing flow in our implementation. In addition to the knowledge transfer scheme, we examine how configuration of the distillation positions impacts on the knowledge transfer performance. To evaluate the proposed ideas, we choose two knowledge distillation baseline models which are based on Normalizing flow on different domains: CS-Flow for anomaly detection and SRFlow-DA for super-resolution. A set of performance comparison to the baseline models with popular benchmark datasets shows promising results along with improved inference speed. The comparison includes performance analysis based on various configurations of the distillation positions in the proposed scheme.

Video-based action recognition encompasses the recognition of appearance and the classification of action types. This work proposes a discrete-temporal-sequence-based motion tendency clustering framework to implement motion clustering by extracting motion tendencies and self-supervised learning. A published traffic intersection dataset (inD) and a self-produced gesture video set are used for evaluation and to validate the motion tendency action recognition hypothesis.